UROP Research Mentor Project Submission Portal: Submission #1310
Submission information
Submission Number: 1310
Submission ID: 21146
Submission UUID: 8f982364-4b37-4ebf-945c-eeecf8b33993
Submission URI: /urop-research-mentor-project-submission-portal
Submission Update: /urop-research-mentor-project-submission-portal?token=u2vtkWi8wWtNhLajkAoNomiHcHy-9hseS-Y8mSctfrE
Created: Thu, 08/21/2025 - 08:08 PM
Completed: Thu, 08/21/2025 - 08:09 PM
Changed: Mon, 08/25/2025 - 11:25 AM
Remote IP address: 69.254.218.185
Submitted by: Anonymous
Language: English
Is draft: No
Webform: UROP Project Proposal Portal
Submitted to: UROP Research Mentor Project Submission Portal
Research Mentor Information
Zhixin Pan
{Empty}
zp23e@fsu.edu
Faculty
FAMU-FSU College of Engineering
Department of Electrical and Computer Engineering
{Empty}
Additional Research Mentor(s)
{Empty}
{Empty}
{Empty}
{Empty}
{Empty}
{Empty}
{Empty}
{Empty}
Overall Project Details
Lightweight Malware Detector using Machine Learning
Machine Learning, Cybersecurity, High-performance Computing
Yes
2
Computer Science (CS)
Electrical and Computer Engineering (ECE)
Electrical and Computer Engineering (ECE)
FAMU–FSU College of Engineering (Innovation Park, 2525 Pottsdamer St.) / Center for Advanced Power Systems.
No, the project is remote
Fully Remote
5-10
Flexible schedule (Combination of business and outside of business. TBD between student and research mentor.)
Malware and ransomware continue to evolve, creating challenges for traditional defense systems. This project investigates lightweight zero-shot malware detection, where machine learning models can identify new threats without requiring extensive retraining. We will focus on making models efficient through advanced machine learning techniques, including quantization and contrastive learning. Students will begin with public malware datasets, building baseline models and exploring how these techniques improve detection performance. This project offers hands-on experience at the intersection of cybersecurity and artificial intelligence, with opportunities to present results at FSU’s Undergraduate Research Symposium and potentially contribute to a research publication.
UROP students will participate in the following activities:
1. Data Preparation – Download and organize publicly available malware datasets (e.g., EMBER, Malimg) and perform basic preprocessing.
2. Literature Reviewing - Survey existing research on machine learning for malware detection, focusing on lightweight methods and zero-shot or few-shot learning.
3. Baseline Modeling – Train and test simple machine learning models (e.g., Random Forest, Support Vector Machines, basic neural networks) using Python and scikit-learn.
4. Lightweight Models – Apply quantization techniques to reduce model size and improve efficiency while monitoring accuracy trade-offs.
5. Zero-Shot Learning – Explore contrastive learning approaches to enable the system to detect previously unseen malware families.
6. Evaluation & Communication – Analyze results, prepare figures/tables, and present findings at the Undergraduate Research Symposium in the spring.
1. Data Preparation – Download and organize publicly available malware datasets (e.g., EMBER, Malimg) and perform basic preprocessing.
2. Literature Reviewing - Survey existing research on machine learning for malware detection, focusing on lightweight methods and zero-shot or few-shot learning.
3. Baseline Modeling – Train and test simple machine learning models (e.g., Random Forest, Support Vector Machines, basic neural networks) using Python and scikit-learn.
4. Lightweight Models – Apply quantization techniques to reduce model size and improve efficiency while monitoring accuracy trade-offs.
5. Zero-Shot Learning – Explore contrastive learning approaches to enable the system to detect previously unseen malware families.
6. Evaluation & Communication – Analyze results, prepare figures/tables, and present findings at the Undergraduate Research Symposium in the spring.
Required:
Basic programming experience (preferably in Python)
Familiarity with data handling tools (e.g., Excel, pandas, or similar)
Recommended:
Interest in machine learning and cybersecurity
Ability to read and summarize academic articles for a literature review
Strong attention to detail and willingness to learn new tools
Basic programming experience (preferably in Python)
Familiarity with data handling tools (e.g., Excel, pandas, or similar)
Recommended:
Interest in machine learning and cybersecurity
Ability to read and summarize academic articles for a literature review
Strong attention to detail and willingness to learn new tools
My mentoring philosophy is to create a supportive, engaging environment where students can grow as researchers and critical thinkers. I begin by learning about each student’s goals, motivations, and current skill set. Together, we set clear and achievable milestones that help students gain confidence while gradually increasing the technical and intellectual depth of their work.
I believe in giving mentees ownership of their projects. Students are expected to take responsibility for their tasks, but they are never left without support. I encourage them to ask questions, share ideas, and learn from challenges in a safe environment where mistakes are viewed as opportunities to improve. Open communication and mutual respect are central to this process.
To provide layered mentoring, I involve graduate students in my lab as day-to-day guides, while I provide higher-level direction, regular check-ins, and professional development advice. This structure ensures that undergraduates receive practical training as well as broader context for their research.
I believe in giving mentees ownership of their projects. Students are expected to take responsibility for their tasks, but they are never left without support. I encourage them to ask questions, share ideas, and learn from challenges in a safe environment where mistakes are viewed as opportunities to improve. Open communication and mutual respect are central to this process.
To provide layered mentoring, I involve graduate students in my lab as day-to-day guides, while I provide higher-level direction, regular check-ins, and professional development advice. This structure ensures that undergraduates receive practical training as well as broader context for their research.
https://scholar.google.com/citations?hl=en&user=iCt6DooAAAAJ
{Empty}
No
{Empty}
UROP Program Elements
Yes
Yes
Yes
Yes
{Empty}
2025
https://cre.fsu.edu/urop-research-mentor-project-submission-portal?token=u2vtkWi8wWtNhLajkAoNomiHcHy-9hseS-Y8mSctfrE